© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1579
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron primarily responds to action-directing verbs—especially second-person imperatives or calls to action.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =
    0.53
    '
    0.52
    -
    0.47
     -
    0.46
    .
    0.46
     lunes
    0.45
    ,
    0.45
    ’
    0.44
    +
    0.43
     delas
    0.42
    POSITIVE LOGITS
    出一
    0.45
     një
    0.44
    ла
    0.43
    出一个
    0.43
    ٹ
    0.43
    zló
    0.43
    ز
    0.43
     جميع
    0.42
     самую
    0.42
    một
    0.42
    Activations Density 3.143%

    No Known Activations